WEBVTT

00:00:00.000 --> 00:00:03.472 align:middle line:90%
[MUSIC PLAYING]

00:00:03.472 --> 00:00:15.890 align:middle line:90%


00:00:15.890 --> 00:00:18.530 align:middle line:84%
Hello, and welcome
to a quick tutorial

00:00:18.530 --> 00:00:22.370 align:middle line:84%
on how to calculate a
correlation using PSPP.

00:00:22.370 --> 00:00:25.680 align:middle line:84%
Now, I've gone ahead and opened
up the correlation.sav file.

00:00:25.680 --> 00:00:28.250 align:middle line:84%
This is the file that
corresponds with the example

00:00:28.250 --> 00:00:31.040 align:middle line:84%
from the textbook
on correlations.

00:00:31.040 --> 00:00:32.600 align:middle line:84%
In this case, we
wanted to find out

00:00:32.600 --> 00:00:34.820 align:middle line:84%
if there is a relationship
between an individual's

00:00:34.820 --> 00:00:36.590 align:middle line:84%
level of communication
apprehension,

00:00:36.590 --> 00:00:39.140 align:middle line:84%
which we have up here,
and their heart rate

00:00:39.140 --> 00:00:41.600 align:middle line:84%
change while giving
a public speech.

00:00:41.600 --> 00:00:45.731 align:middle line:84%
So we have one
interval variable,

00:00:45.731 --> 00:00:47.230 align:middle line:84%
which is communication
apprehension,

00:00:47.230 --> 00:00:50.220 align:middle line:84%
and we have one ratio variable,
which is heart rate change.

00:00:50.220 --> 00:00:52.387 align:middle line:84%
So let's look at how we can
actually correlate that.

00:00:52.387 --> 00:00:53.969 align:middle line:84%
First thing we're
going to do is we're

00:00:53.969 --> 00:00:55.160 align:middle line:90%
going to go up to Analyze.

00:00:55.160 --> 00:00:58.040 align:middle line:84%
We're then going to scroll
down to Bivariate Correlation,

00:00:58.040 --> 00:00:59.540 align:middle line:90%
and I'm going to click on that.

00:00:59.540 --> 00:01:02.882 align:middle line:84%
And then all I have to do is
select the two variables that I

00:01:02.882 --> 00:01:04.340 align:middle line:84%
want and click that
arrow, and it's

00:01:04.340 --> 00:01:06.962 align:middle line:84%
going to send them over
to that box right there.

00:01:06.962 --> 00:01:08.420 align:middle line:84%
And this is the
box that ultimately

00:01:08.420 --> 00:01:09.545 align:middle line:90%
where the correlations are.

00:01:09.545 --> 00:01:11.810 align:middle line:84%
Now, we do want to go ahead
and flag significant ones.

00:01:11.810 --> 00:01:13.530 align:middle line:90%
It just makes it easier to see.

00:01:13.530 --> 00:01:15.500 align:middle line:84%
So I went ahead and
put that check mark in.

00:01:15.500 --> 00:01:17.270 align:middle line:90%
And then I can just click OK.

00:01:17.270 --> 00:01:20.550 align:middle line:84%
And this is ultimately
what it looks like.

00:01:20.550 --> 00:01:22.700 align:middle line:90%
So, here's what we have here.

00:01:22.700 --> 00:01:25.760 align:middle line:84%
We have a Pearson product-moment
correlation was calculated.

00:01:25.760 --> 00:01:28.890 align:middle line:90%
And they have it at 0.91.

00:01:28.890 --> 00:01:31.160 align:middle line:84%
So, that is, again,
a strong correlation.

00:01:31.160 --> 00:01:34.040 align:middle line:84%
And the p-value
here is at 0.000,

00:01:34.040 --> 00:01:36.470 align:middle line:84%
which is definitely
less than 0.01.

00:01:36.470 --> 00:01:37.970 align:middle line:84%
Don't forget, that
would be reported

00:01:37.970 --> 00:01:42.650 align:middle line:84%
as p is less than
0.001 in APA style.

00:01:42.650 --> 00:01:44.750 align:middle line:84%
And then we have the
number of participants.

00:01:44.750 --> 00:01:46.376 align:middle line:90%
In this case, it was 20.

00:01:46.376 --> 00:01:47.750 align:middle line:84%
Now, one thing to
notice, though,

00:01:47.750 --> 00:01:50.540 align:middle line:84%
whenever you're looking
at a correlation matrix

00:01:50.540 --> 00:01:54.050 align:middle line:84%
is, you have this diagonal
column here of what we

00:01:54.050 --> 00:01:55.880 align:middle line:90%
call perfect correlations.

00:01:55.880 --> 00:01:58.100 align:middle line:84%
That is the score of
communication apprehension

00:01:58.100 --> 00:02:00.580 align:middle line:84%
being correlated with that
person's score of communication

00:02:00.580 --> 00:02:03.770 align:middle line:84%
apprehension or the score of
heart rate being calculated

00:02:03.770 --> 00:02:05.030 align:middle line:90%
with the score of heart rate.

00:02:05.030 --> 00:02:08.750 align:middle line:84%
Since it's the same number,
it's always going to be a 1.

00:02:08.750 --> 00:02:11.510 align:middle line:84%
Hence, why we get this
diagonal line of 1s.

00:02:11.510 --> 00:02:13.790 align:middle line:84%
What that does mean,
though, is that we end up

00:02:13.790 --> 00:02:16.500 align:middle line:84%
with two sets of
reported values.

00:02:16.500 --> 00:02:18.724 align:middle line:84%
So, in this case, we have
communication apprehension

00:02:18.724 --> 00:02:20.390 align:middle line:84%
with heart rate change,
and down here we

00:02:20.390 --> 00:02:23.360 align:middle line:84%
have heart rate change with
communication apprehension.

00:02:23.360 --> 00:02:26.060 align:middle line:84%
You'll notice that the
information in this box here

00:02:26.060 --> 00:02:30.240 align:middle line:84%
and the information in
this box here is identical.

00:02:30.240 --> 00:02:32.270 align:middle line:84%
Now, that's easy to think
about, but we always

00:02:32.270 --> 00:02:34.186 align:middle line:84%
want to make sure that
we are paying attention

00:02:34.186 --> 00:02:36.110 align:middle line:84%
so that we look at that
diagonal line of 1s

00:02:36.110 --> 00:02:40.400 align:middle line:84%
and then only report one
side of that diagonal when

00:02:40.400 --> 00:02:42.200 align:middle line:90%
it comes to reporting results.

00:02:42.200 --> 00:02:44.552 align:middle line:84%
Personally, I always do
the ones up to the right,

00:02:44.552 --> 00:02:46.760 align:middle line:84%
but you could just as easily
do the ones to the left.

00:02:46.760 --> 00:02:47.830 align:middle line:90%
That's just up to you.

00:02:47.830 --> 00:02:49.910 align:middle line:84%
And this is important
when we start dealing

00:02:49.910 --> 00:02:51.810 align:middle line:90%
with larger correlations.

00:02:51.810 --> 00:02:54.440 align:middle line:84%
So let's go ahead and look
at a real larger correlation.

00:02:54.440 --> 00:02:57.770 align:middle line:84%
I'm now going to open up that
Textbook Data Set Shortened.

00:02:57.770 --> 00:02:59.690 align:middle line:90%
And I'm going to click Open.

00:02:59.690 --> 00:03:01.664 align:middle line:84%
So now we have a
much larger data set.

00:03:01.664 --> 00:03:03.080 align:middle line:84%
And so what I'm
going to do is I'm

00:03:03.080 --> 00:03:04.455 align:middle line:84%
going to come up
here to Analyze,

00:03:04.455 --> 00:03:06.680 align:middle line:84%
and I'm going to go to
Bivariate Correlation.

00:03:06.680 --> 00:03:08.810 align:middle line:84%
I'm going to scroll
down, and I'm

00:03:08.810 --> 00:03:11.750 align:middle line:84%
going to find a couple of
different variables to look at.

00:03:11.750 --> 00:03:14.270 align:middle line:84%
We're going to do
communication apprehension.

00:03:14.270 --> 00:03:18.050 align:middle line:84%
We'll do it with assertiveness
and responsiveness.

00:03:18.050 --> 00:03:21.200 align:middle line:84%
And we'll also correlate
them with willingness

00:03:21.200 --> 00:03:22.440 align:middle line:90%
to communicate.

00:03:22.440 --> 00:03:23.920 align:middle line:90%
So we have four variables.

00:03:23.920 --> 00:03:25.670 align:middle line:84%
So let's go ahead
and look at that.

00:03:25.670 --> 00:03:28.790 align:middle line:84%
And again, I'm going to click
Flag Significant Correlations.

00:03:28.790 --> 00:03:30.470 align:middle line:90%
And I'm going to click OK.

00:03:30.470 --> 00:03:34.290 align:middle line:84%
And here is now what the
PSPP output looks like.

00:03:34.290 --> 00:03:36.950 align:middle line:84%
So, now, first thing
to do is, again,

00:03:36.950 --> 00:03:40.120 align:middle line:90%
find that diagonal line of 1s.

00:03:40.120 --> 00:03:42.710 align:middle line:84%
And you can see this
is four, and it already

00:03:42.710 --> 00:03:44.640 align:middle line:90%
gets a lot more complex.

00:03:44.640 --> 00:03:46.970 align:middle line:84%
So if you had something
like 10 different variables

00:03:46.970 --> 00:03:49.760 align:middle line:84%
that you're analyzing, you can
see how these matrices just

00:03:49.760 --> 00:03:51.200 align:middle line:90%
get larger and larger.

00:03:51.200 --> 00:03:55.070 align:middle line:84%
So it's always important to
find that line of diagonals

00:03:55.070 --> 00:03:59.084 align:middle line:84%
so you're only reporting one
side of the relationships.

00:03:59.084 --> 00:04:01.250 align:middle line:84%
So, in this case, we have
communication apprehension

00:04:01.250 --> 00:04:04.490 align:middle line:84%
is negative related
to assertiveness.

00:04:04.490 --> 00:04:07.070 align:middle line:84%
It's not statistically
significantly related

00:04:07.070 --> 00:04:08.997 align:middle line:90%
to responsiveness.

00:04:08.997 --> 00:04:10.580 align:middle line:84%
Communication
apprehension is negative

00:04:10.580 --> 00:04:13.580 align:middle line:84%
related to the person's
willingness to communicate.

00:04:13.580 --> 00:04:17.980 align:middle line:84%
Assertiveness is positive
related to responsiveness,

00:04:17.980 --> 00:04:20.209 align:middle line:84%
though it's a very
small relationship.

00:04:20.209 --> 00:04:21.589 align:middle line:90%
It's minimal.

00:04:21.589 --> 00:04:25.400 align:middle line:84%
It's also minimally related
to willingness to communicate.

00:04:25.400 --> 00:04:27.830 align:middle line:84%
And then, last but not
least, we have responsiveness

00:04:27.830 --> 00:04:31.070 align:middle line:84%
is positively related to
a person's willingness

00:04:31.070 --> 00:04:32.259 align:middle line:90%
to communicate.

00:04:32.259 --> 00:04:34.550 align:middle line:84%
So again, the big thing--
and notice what I was doing--

00:04:34.550 --> 00:04:39.920 align:middle line:84%
is only reporting these over
here on, for my purposes,

00:04:39.920 --> 00:04:43.400 align:middle line:84%
the right side of that
diagonal line of 1s.

00:04:43.400 --> 00:04:45.920 align:middle line:84%
You could, again, just as
easily had done the left side.

00:04:45.920 --> 00:04:49.490 align:middle line:84%
You just want to make sure that
you're only reporting one side.

00:04:49.490 --> 00:04:53.300 align:middle line:84%
And that is how you can run and
understand correlation matrices

00:04:53.300 --> 00:04:55.350 align:middle line:90%
using PSPP.

00:04:55.350 --> 00:04:58.700 align:middle line:90%
[MUSIC PLAYING]

00:04:58.700 --> 00:05:09.590 align:middle line:90%